Granted Patent B2

US 12,245,044 · App. 18/405,508 · Granted Mar 4, 2025

Inventors: Armando Montalvo (Winter Garden, FL); Jeremy Levin (Virginia Beach, VA); Dwight Inman (Travelers Rest, SC); Edward Hummel (Hillsborough, NJ)

Assignee: Digital Global Systems, Inc.

H04W16/10G06F30/27G06N3/02G06N5/022G06N5/04G06N20/00G06N20/10G06N20/20H04L41/0893H04W24/02H04W72/0453G06N3/042G06N3/045H04L41/0894H04W16/14H04W24/08

Abstract

Claims (53)

1. A system for predicting and mitigating interference in an electromagnetic environment comprising:

at least one monitoring sensor operable to monitor the electromagnetic environment and create measured data based on the electromagnetic environment, wherein the at least one monitoring sensor is in communication with a learning engine, at least one data analysis engine, a semantic engine, and at least one server;

wherein the learning engine is operable to learn the electromagnetic environment; and

wherein the at least one server is operable to create actionable data;

wherein the learning engine is operable to provide predictive analytics for the electromagnetic environment based on the measured data using machine learning (ML), artificial intelligence (AI), deep learning (DL), neural networks (NNs), artificial neural networks (ANNs), support vector machines (SVMs), Markov decision process (MDP), natural language processing (NLP), control theory, and/or statistical learning techniques;

wherein the predictive analytics includes performing interference modeling;

wherein the learning engine is operable to predict interference in the electromagnetic environment based on the interference modeling;

wherein the at least one data analysis engine includes an identification engine operable to identify a device or an emitter transmitting at least one signal of interest;

wherein the at least one server creates the actionable data based on the predicted interference, analyzed data from the at least one data analysis engine, and information relating to a rule or a policy;

wherein the semantic engine is operable to establish the rule or the policy based on converting a user data input into the actionable data using natural language processing (NLP);

wherein the user data input includes at least one use case and/or at least one objective; and

wherein the at least one server is operable to send at least one notification based on the actionable data in real time or near real time.

2. The system of claim 1 , wherein the learning engine is operable to provide the predictive analytics for the electromagnetic environment based on external data sources.

3. The system of claim 1 , wherein the learning engine is operable to autonomously provide the predictive analytics.

4. The system of claim 1 , wherein the learning engine is operable to modify a training data set for a ML model, an AI model, a DL model, or a NN model.

5. The system of claim 1 , wherein a learning engine software development kit (SDK) is operable to convert a training model for operation in another electromagnetic environment.

6. The system of claim 5 , wherein the training model includes a ML model, an AI model, a DL model, or a NN model.

7. The system of claim 1 , wherein the actionable data relates to interference mitigation or interference prevention.

8. The system of claim 1 , wherein the system is operable to automatically establish a set of de-confliction rules.

9. The system of claim 1 , wherein the system is operable to provide reconfiguration options relating to time, frequency, and/or spatial settings.

10. A system for predicting and mitigating interference in an electromagnetic environment comprising:

at least one monitoring sensor operable to monitor the electromagnetic environment and create measured data based on the electromagnetic environment;

at least one data analysis engine;

a semantic engine; and

a learning engine operable to provide predictive analytics for the electromagnetic environment based on the measured data using machine learning (ML), artificial intelligence (AI), deep learning (DL), neural networks (NNs), artificial neural networks (ANNs), support vector machines (SVMs), Markov decision process (MDP), natural language processing (NLP), control theory, and/or statistical learning techniques;

wherein the at least one monitoring sensor is in communication with the learning engine;

wherein the at least one data analysis engine includes an identification engine operable to identify a device or an emitter transmitting at least one signal of interest;

wherein the predictive analytics includes performing interference modeling;

wherein the learning engine is operable to predict interference in the electromagnetic environment based on the interference modeling;

wherein the learning engine is operable to modify a training data set for a ML model, an AI model, a DL model, or a NN model; and

wherein the system is operable to provide reconfiguration options relating to time, frequency, and/or spatial settings and/or actionable data based on the predictive analytics, analyzed data from the at least one data analysis engine, and information relating to a rule or a policy;

wherein the semantic engine is operable to establish the rule or the policy and converting a user data input into the actionable data using natural language processing (NLP);

wherein the user data input includes at least one use case and/or at least one objective; and

wherein the system is operable to send at least one notification based on the actionable data.

11. The system of claim 10 , further comprising at least one server operable to create the actionable data and/or the reconfiguration options.

12. The system of claim 10 , wherein the learning engine is operable to provide the predictive analytics for the electromagnetic environment based on external data sources.

13. The system of claim 10 , wherein the learning engine is operable to autonomously provide the predictive analytics.

14. The system of claim 10 , wherein the training data set is operable to be modified for operation in another environment.

15. The system of claim 10 , wherein the actionable data relates to interference mitigation or interference prevention.

16. A method for predicting and mitigating interference in an electromagnetic environment comprising:

at least one monitoring sensor monitoring the electromagnetic environment and creating measured data based on the electromagnetic environment;

at least one data analysis engine identifying a device or an emitter transmitting at least one signal of interest; and

a learning engine providing predictive analytics for the electromagnetic environment based on the measured data using machine learning (ML), artificial intelligence (AI), deep learning (DL), neural networks (NNs), artificial neural networks (ANNs), support vector machines (SVMs), Markov decision process (MDP), natural language processing (NLP), control theory, and/or statistical learning techniques;

wherein the at least one monitoring sensor is in communication with the learning engine;

wherein the predictive analytics includes performing interference modeling;

the learning engine predicting interference in the electromagnetic environment based on the interference modeling;

providing reconfiguration options relating to time, frequency, and/or spatial settings and/or providing actionable data based on the predictive analytics, analyzed data from the at least one data analysis engine, and information relating to a rule or a policy;

at least one semantic engine establishing the rule or the policy based on converting a user data input into the actionable data using natural language processing (NLP), wherein the user data input includes at least one use case and/or at least one objective; and

sending at least one notification based on the actionable data in real time or near real time.

17. The method of claim 16 , further comprising modifying a training data set for a ML model, an AI model, a DL model, or a NN model.

18. The method of claim 16 , wherein the learning engine provides the predictive analytics for the electromagnetic environment based on external data sources.

19. The method of claim 16 , wherein the learning engine provides the predictive analytics autonomously.

20. The method of claim 16 , wherein the actionable data relates to interference mitigation or interference prevention.

Assignments (2)

Continuity (8)

References Cited (393)

Cited By (2)

US 12,382,302 US 12,464,371